Stable Diffusion 3.5
Collection
6 items • Updated • 182
Shivay Lamba
shivaylamba
·
AI & ML interests
TensorFlowJS, LLMs, RAG, MLOps, Flyte, KubeFlow, TensorFlow, Transformers.js, Onnx, WebAssembly
Recent Activity
upvoted a collection 6 days ago
Stable Diffusion 3.5 updated a Space 7 months ago
shivaylamba/testspace published a Space 7 months ago
shivaylamba/testspaceOrganizations
upvoted a collection 6 days ago
updated a
Space 7 months ago
published a
Space 7 months ago
reacted to bhalajin's post with 🔥 about 1 year ago
Post
1659
###### CVPR2025 Workshop Challenge Alert ######
🫠 Between deadlines, rebuttals, and existential crises??? "We got you!!!!"
📢 Our new CVPR25 multi-modal challenge is online !!!
🍽️ Dishcovery: VLM MetaFood Challenge!!!! 🍽️
😋🧫 Can your groundbreaking VLM understand the difference between sushi styles, pasta types, or cooking methods from just image + caption pairs?
🌐 Our Task: Match fine-grained images to food descriptions
Challenge Highlights:
📦 400K food image-caption pairs, a little taste to get you started !!!
🔬 Got a SoTA VLM? Come test it on our challenging test sets !!!
🎯 Challenge for everyone! Easy to use SigLIP baseline is provided !!!
🔍 Real, synthetic, noisy data – just like real life - Will your VLM redefine how people track their diets??? ( 🗣️ We believe so!!! )
🔗 Join the challenge: https://www.kaggle.com/competitions/dishcovery-vlm-mtf-cvpr-2025
🗓️ Deadline: Phase I: 4th of May, 2025 - Phase II: 10th of May, 2025
👉 Workshop website: https://sites.google.com/view/cvpr-metafood-2025
#CVPR25 #ComputerVision #CV #Deeplearning #DL #VisionLanguage #VLM #multimodal #FoundationModels
🫠 Between deadlines, rebuttals, and existential crises??? "We got you!!!!"
📢 Our new CVPR25 multi-modal challenge is online !!!
🍽️ Dishcovery: VLM MetaFood Challenge!!!! 🍽️
😋🧫 Can your groundbreaking VLM understand the difference between sushi styles, pasta types, or cooking methods from just image + caption pairs?
🌐 Our Task: Match fine-grained images to food descriptions
Challenge Highlights:
📦 400K food image-caption pairs, a little taste to get you started !!!
🔬 Got a SoTA VLM? Come test it on our challenging test sets !!!
🎯 Challenge for everyone! Easy to use SigLIP baseline is provided !!!
🔍 Real, synthetic, noisy data – just like real life - Will your VLM redefine how people track their diets??? ( 🗣️ We believe so!!! )
🔗 Join the challenge: https://www.kaggle.com/competitions/dishcovery-vlm-mtf-cvpr-2025
🗓️ Deadline: Phase I: 4th of May, 2025 - Phase II: 10th of May, 2025
👉 Workshop website: https://sites.google.com/view/cvpr-metafood-2025
#CVPR25 #ComputerVision #CV #Deeplearning #DL #VisionLanguage #VLM #multimodal #FoundationModels
updated 3
models almost 2 years ago
updated a
Space over 2 years ago
liked a
Space over 2 years ago
updated a
Space over 2 years ago